Topic Group Dental Diagnostics and Digital Dentistry, ITU/WHO Focus Group, AI On Health, Berlin, Germany.
Executive Secretary of Research Committee, Board Director of Scientific Society, Dental Faculty, Azad University, Tehran, Iran.
Oral Radiol. 2024 Jan;40(1):1-20. doi: 10.1007/s11282-023-00715-5. Epub 2023 Oct 19.
This study aims to review deep learning applications for detecting head and neck cancer (HNC) using magnetic resonance imaging (MRI) and radiographic data.
Through January 2023, a PubMed, Scopus, Embase, Google Scholar, IEEE, and arXiv search were carried out. The inclusion criteria were implementing head and neck medical images (computed tomography (CT), positron emission tomography (PET), MRI, Planar scans, and panoramic X-ray) of human subjects with segmentation, object detection, and classification deep learning models for head and neck cancers. The risk of bias was rated with the quality assessment of diagnostic accuracy studies (QUADAS-2) tool. For the meta-analysis diagnostic odds ratio (DOR) was calculated. Deeks' funnel plot was used to assess publication bias. MIDAS and Metandi packages were used to analyze diagnostic test accuracy in STATA.
From 1967 studies, 32 were found eligible after the search and screening procedures. According to the QUADAS-2 tool, 7 included studies had a low risk of bias for all domains. According to the results of all included studies, the accuracy varied from 82.6 to 100%. Additionally, specificity ranged from 66.6 to 90.1%, sensitivity from 74 to 99.68%. Fourteen studies that provided sufficient data were included for meta-analysis. The pooled sensitivity was 90% (95% CI 0.820.94), and the pooled specificity was 92% (CI 95% 0.87-0.96). The DORs were 103 (27-251). Publication bias was not detected based on the p-value of 0.75 in the meta-analysis.
With a head and neck screening deep learning model, detectable screening processes can be enhanced with high specificity and sensitivity.
本研究旨在综述使用磁共振成像（MRI）和影像学数据检测头颈部癌症（HNC）的深度学习应用。
截至 2023 年 1 月，我们对 PubMed、Scopus、Embase、Google Scholar、IEEE 和 arXiv 进行了检索。纳入标准为：实施了针对头颈部医学图像（计算机断层扫描（CT）、正电子发射断层扫描（PET）、MRI、平面扫描和全景 X 射线）的人体分割、目标检测和分类深度学习模型，用于头颈部癌症。使用诊断准确性研究质量评估工具（QUADAS-2）评估偏倚风险。对于荟萃分析，计算了诊断比值比（DOR）。使用 Deeks 漏斗图评估发表偏倚。使用 MIDAS 和 Metandi 包在 STATA 中分析诊断测试准确性。
经过搜索和筛选程序，从 1967 项研究中找到了 32 项符合条件的研究。根据 QUADAS-2 工具，7 项纳入研究在所有领域均具有低偏倚风险。根据所有纳入研究的结果，准确性范围从 82.6%到 100%不等。此外，特异性范围从 66.6%到 90.1%，敏感性从 74%到 99.68%。纳入了 14 项提供了足够数据的研究进行荟萃分析。汇总敏感性为 90%（95%CI 0.820.94），汇总特异性为 92%（95%CI 0.87-0.96）。DOR 为 103（27-251）。荟萃分析的 p 值为 0.75，未检测到发表偏倚。
使用头颈部筛查深度学习模型，可以提高检测的特异性和敏感性，从而增强筛查过程。
